© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 191744
    Prev
    Next
    INDEX
    Explanations

    YouTube links and product descriptions

    np_acts-logits-general · gemini-2.5-flash-lite

    neural network activity and function

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     passar
    0.51
     Veranstaltung
    0.50
     Verhalten
    0.50
    䀘
    0.50
     ইং
    0.48
     ব্রিটিশ
    0.47
     setzen
    0.47
     Sehingga
    0.47
     পেরিয়ে
    0.47
    焖
    0.46
    POSITIVE LOGITS
     schematically
    0.46
    membered
    0.46
    save
    0.45
    roon
    0.44
    rest
    0.44
     srcs
    0.43
     muck
    0.42
    table
    0.42
    src
    0.41
    insert
    0.41
    Activations Density 0.000%

    No Known Activations